Multi-Sentence Argument Linking

TL;DR

This paper introduces a new neural model for linking argument spans across sentences in documents, supported by a large annotated dataset called RAMS, improving event role filling and semantic understanding.

Contribution

The paper presents a novel document-level argument linking model and introduces RAMS, a large dataset for cross-sentence event role annotation.

Findings

Strong performance on RAMS dataset

Effective cross-sentence argument linking

Improved event role filling accuracy

Abstract

We present a novel document-level model for finding argument spans that fill an event's roles, connecting related ideas in sentence-level semantic role labeling and coreference resolution. Because existing datasets for cross-sentence linking are small, development of our neural model is supported through the creation of a new resource, Roles Across Multiple Sentences (RAMS), which contains 9,124 annotated events across 139 types. We demonstrate strong performance of our model on RAMS and other event-related datasets.